[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122167-en":3,"doc-seo-122167-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122167,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","XAI Beyond Classification - Interpretable Neural Clustering","A research paper examining two core challenges at the intersection of explainable AI (XAI) and data clustering: building neural networks with inherent interpretability instead of relying on post-hoc explanations, and implementing k-means in a differentiable form for efficient learning. It introduces TELL, a differentiable neural reformulation of vanilla k-means designed to preserve k-means advantages such as online clustering, parallel computing, plug-and-play integration, and provable convergence. Experiments on three challenging datasets show performance gains over 14 clustering baselines.","arXiv : 1808 .07292v3 [ cs .LG] 22 Apr 2022  \nXAI Beyond Classification: Interpretable Neural Clustering  \nXi Peng 1 PENGX . GM @ GMAIL . COM  \nYunfan Li 1 YUNFANLI. GM @ GMAIL . COM  \nIvor W. Tsang2 ;3 IVOR . TSANG @ GMAIL . COM  \nHongyuan Zhu4 ZHUH @I2R . A-STAR . EDU . SG  \nJiancheng Lv 1 􀀃 LVJIANCHENG @ SCU . EDU . CN  \nJoey Tianyi Zhou3 ;5 JOEY. TIANYI. ZHOU @ GMAIL . COM  \n1 College of Computer Science, Sichuan University, Chengdu, China.  \n2 Centre for Frontier Artificial Intelligence Research, A*STAR, Singapore.  \n3 Australian Artificial Intelligence Institute, University of Technology, Sydney Australia.  \n4 Institute for Infocomm Research, A*STAR, Singapore.  \n5 Institute of High Performance Computing, A*STAR, Singapore.  \nEditor: David Blei  \nAbstract  \nIn this paper, we study two challenging problems in explainable AI (XAI) and data clustering. The first is how to directly design a neural network with inherent interpretability, rather than giving post-hoc explanations of a black-box model. The second is implementing discrete k-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning. To address these two challenges, we design a novel neural network, which is a differentiable reformulation of the vanilla k-means, called inTerpretable nEuraL cLustering (TELL) . Our contributions are threefold. First, to the best of our knowledge, most existing XAI works focus on supervised learning paradigms. This work is oneof the few XAI studies on unsupervised learning, in particular, data clustering. Second, TELL isan interpretable, or the so-called intrinsically explainable and transparent model. In contrast, most existing XAI studies resort to various means for understanding a black-box model with post-hoc explanations. Third, from the view of data clustering, TELL possesses many properties highly desired by k-means, including but not limited to online clustering, plug-and-play module, parallel computing, and provable convergence. Extensive experiments show that our method achieves superior performance comparing with 14 clustering approaches on three challenging data sets. The source code could be [accessed at](accessed at www.pengxi.me)[ www.pengxi.me](accessed at www.pengxi.me).  \nKeywords: transparent neural networks, stochastic k-means clustering, differentiable programming.  \n1. Introduction  \nAs a fundamental topic in machine learning, clustering aims to group similar samples into the same cluster and separate dissimilar ones into different clusters. During the past decade, a variety of  \n* . Corresponding author.  \n©2021 Xi Peng, Yunfan Li, Ivor Tsang, Hongyuan Zhu, Jiancheng Lv, and Joey Tianyi Zhou.  \nLicense: CC-BY 4.0, see [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/. Attribution requirements)[. Attribution requirements](https://creativecommons.org/licenses/by/4.0/. Attribution requirements) are provided at  \n[http://jmlr.org/papers/v22/19-497.html](http://jmlr.org/papers/v22/19-497.html).  \nPENG, LI, TSANG, ZHU, LV, AND ZHOU .  \nclustering methods (Jain et al., 1999) have been proposed and achieved encouraging success in various applications. In recent, the main focus of the community shifts to how to handle highdimensional data that is usually linear inseparable.  \nTo effectively cluster high-dimensional data, many kinds of methods have been proposed, e.g., spectral clustering (Ng et al., 2001), kernel clustering (Wang et al., 2019), convex clustering (Hocking et al., 2011; Yi et al., 2013), subspace clustering (Elhamifar and Vidal, 2013; Liu et al., 2013; Lu et al., 2012; Yang et al., 2018; Li et al., 2015), and the recent popular deep clustering (Yang et al., 2016; Peng et al., 2016; Ji et al., 2017) . The aforementioned methods share a common clustering paradigm of first learning a shallow or deep representation and then applying a traditional clustering method (k-mea","cbCaiiKU60QmMCWJ","https://ap.wps.com/l/cbCaiiKU60QmMCWJ","pdf",1715339,1,28,"English","en",105,"# Introduction\n## Clustering background and motivation\n## Limitations of traditional and deep clustering\n## Proposed TELL approach and contributions","[{\"question\":\"What problem does the paper address in explainable AI for clustering?\",\"answer\":\"It focuses on designing neural models that are intrinsically interpretable for clustering, avoiding reliance on post-hoc explanations of black-box networks.\"},{\"question\":\"How is TELL related to vanilla k-means?\",\"answer\":\"TELL is a differentiable reformulation of vanilla k-means that turns the k-means objective into a neural layer for end-to-end optimization.\"},{\"question\":\"What practical benefits does TELL claim compared with vanilla k-means?\",\"answer\":\"It supports online clustering, plug-and-play usage, parallel computing, and provides provable convergence properties.\"}]","XAI Beyond Classification - Interpretable Neural Clustering | PDF",1785809150,71,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"xai-beyond-classication-interpretable-neural-clustering","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/xai-beyond-classication-interpretable-neural-clustering/122167/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in explainable AI for clustering?","Question",{"text":76,"@type":77},"It focuses on designing neural models that are intrinsically interpretable for clustering, avoiding reliance on post-hoc explanations of black-box networks.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is TELL related to vanilla k-means?",{"text":81,"@type":77},"TELL is a differentiable reformulation of vanilla k-means that turns the k-means objective into a neural layer for end-to-end optimization.",{"name":83,"@type":74,"acceptedAnswer":84},"What practical benefits does TELL claim compared with vanilla k-means?",{"text":85,"@type":77},"It supports online clustering, plug-and-play usage, parallel computing, and provides provable convergence properties.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]